© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 229348
    Prev
    Next
    INDEX
    Explanations

    two

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_6_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    s
    1.27
    으로
    1.09
    of
    1.03
    ک
    1.02
    ש
    0.96
    d
    0.95
    로
    0.93
    ur
    0.85
    ને
    0.85
    ید
    0.84
    POSITIVE LOGITS
    你
    1.19
    you
    0.93
    You
    0.90
    ת
    0.89
    ı
    0.89
    -
    0.88
    ла
    0.84
     DON
    0.82
    ing
    0.80
     você
    0.79
    Activations Density 0.000%

    No Known Activations